1. 22 Jun, 2009 2 commits
    • Jaswinder Singh Rajput's avatar
      perf_counter tools: Introduce alias member in event_symbol · 74d5b588
      Jaswinder Singh Rajput authored
      By introducing alias member in event_symbol :
      
      1. duplicate lines are removed, like:
         cpu-cycles and cycles
         branch-instructions and branches
         context-switches and cs
         cpu-migrations and migrations
      
      2. We can also add alias for another events.
      
      Now ./perf list looks like :
      
      List of pre-defined events (to be used in -e):
      
        cpu-cycles OR cycles                     [Hardware event]
        instructions                             [Hardware event]
        cache-references                         [Hardware event]
        cache-misses                             [Hardware event]
        branch-instructions OR branches          [Hardware event]
        branch-misses                            [Hardware event]
        bus-cycles                               [Hardware event]
      
        cpu-clock                                [Software event]
        task-clock                               [Software event]
        page-faults                              [Software event]
        faults                                   [Software event]
        minor-faults                             [Software event]
        major-faults                             [Software event]
        context-switches OR cs                   [Software event]
        cpu-migrations OR migrations             [Software event]
      
        rNNN                                     [raw hardware event descriptor]
      Signed-off-by: default avatarJaswinder Singh Rajput <jaswinderrajput@gmail.com>
      Cc: Peter Zijlstra <peterz@infradead.org>
      LKML-Reference: <1245669268.17153.8.camel@localhost.localdomain>
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      74d5b588
    • Jaswinder Singh Rajput's avatar
      perf_counter tools: Define separate declarations for H/W and S/W events · 51e26842
      Jaswinder Singh Rajput authored
      Define separate declarations for H/W and S/W events to:
      
       1. Shorten name to save some space so that we can add more members
       2. Fix alignment
       3. Avoid declaring HARDWARE/SOFTWARE again and again.
      
      Removed unused CR(x, y)
      Signed-off-by: default avatarJaswinder Singh Rajput <jaswinderrajput@gmail.com>
      Cc: Peter Zijlstra <peterz@infradead.org>
      LKML-Reference: <1245669194.17153.6.camel@localhost.localdomain>
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      51e26842
  2. 21 Jun, 2009 2 commits
    • Ingo Molnar's avatar
      perf_counter tools: Fix vmlinux fallback when running on a different kernel · c1f47b45
      Ingo Molnar authored
      Lucas De Marchi reported that perf report and perf annotate
      displays mismatching profile if a perf.data is analyzed on
      an older kernel - even if the correct vmlinux is specified
      via the -k option.
      
      The reason is the fallback path in util/symbol.c:dso__load_kernel():
      
      int dso__load_kernel(struct dso *self, const char *vmlinux,
                           symbol_filter_t filter, int verbose)
      {
              int err = -1;
      
              if (vmlinux)
                      err = dso__load_vmlinux(self, vmlinux, filter, verbose);
      
              if (err)
                      err = dso__load_kallsyms(self, filter, verbose);
      
              return err;
      }
      
      dso__load_vmlinux() returns negative on error, but on success it
      returns the number of symbols loaded - which confuses the function
      to load the kallsyms.
      
      This is normally harmless, as reporting is usually performed on the
      same kernel that is analyzed - but if there's a mismatch then we
      load the wrong kallsyms and create a non-sensical symbol tree.
      
      The fix is to only fall back to kallsyms on errors.
      Reported-by: default avatarLucas De Marchi <lucas.de.marchi@gmail.com>
      Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
      Cc: Mike Galbraith <efault@gmx.de>
      Cc: Paul Mackerras <paulus@samba.org>
      Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
      LKML-Reference: <new-submission>
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      c1f47b45
    • Jaswinder Singh Rajput's avatar
      perf_counter, x8: Fix L1-data-Cache-Store-Referencees for AMD · d9f2a5ec
      Jaswinder Singh Rajput authored
      Fix AMD's Data Cache Refills from System event.
      
      After this patch :
      
       ./tools/perf/perf stat -e l1d -e l1d-misses -e l1d-write -e l1d-prefetch -e l1d-prefetch-miss -e l1i -e l1i-misses -e l1i-prefetch -e l2 -e l2-misses -e l2-write -e dtlb -e dtlb-misses -e itlb -e itlb-misses -e bpu -e bpu-misses ls /dev/ > /dev/null
      
       Performance counter stats for 'ls /dev/':
      
              2499484  L1-data-Cache-Load-Referencees             (scaled from 3.97%)
                70347  L1-data-Cache-Load-Misses                  (scaled from 7.30%)
                 9360  L1-data-Cache-Store-Referencees            (scaled from 8.64%)
                32804  L1-data-Cache-Prefetch-Referencees         (scaled from 17.72%)
                 7693  L1-data-Cache-Prefetch-Misses              (scaled from 22.97%)
              2180945  L1-instruction-Cache-Load-Referencees      (scaled from 28.48%)
                14518  L1-instruction-Cache-Load-Misses           (scaled from 35.00%)
                 2405  L1-instruction-Cache-Prefetch-Referencees  (scaled from 34.89%)
                71387  L2-Cache-Load-Referencees                  (scaled from 34.94%)
                18732  L2-Cache-Load-Misses                       (scaled from 34.92%)
                79918  L2-Cache-Store-Referencees                 (scaled from 36.02%)
              1295294  Data-TLB-Cache-Load-Referencees            (scaled from 35.99%)
                30896  Data-TLB-Cache-Load-Misses                 (scaled from 33.36%)
              1222030  Instruction-TLB-Cache-Load-Referencees     (scaled from 29.46%)
                  357  Instruction-TLB-Cache-Load-Misses          (scaled from 20.46%)
               530888  Branch-Cache-Load-Referencees              (scaled from 11.48%)
                 8638  Branch-Cache-Load-Misses                   (scaled from 5.09%)
      
          0.011295149  seconds time elapsed.
      
      Earlier it always shows value 0.
      Signed-off-by: default avatarJaswinder Singh Rajput <jaswinderrajput@gmail.com>
      LKML-Reference: <1245484165.3102.6.camel@localhost.localdomain>
      Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
      d9f2a5ec
  3. 20 Jun, 2009 36 commits